SlideShare uma empresa Scribd logo
1 de 17
Latent Diffusion Models
for High Resolution Image
Synthesis
-Akanksha Rawat
SJSU Master’s Student
Image Generation/Synthesis
Generates new images from an existing dataset.
For example, GANs can create images that look like photographs of human faces, even though the faces don't
belong to any real person.
source:
Why it is important: Application areas
❖ Generating synthetic training data if training data is insufficient or collecting it is too costly,
generating human faces and objects in 2D and 3D.
❖ Now with AI being universal, the application extends to using image reconstruction to identify
if someone have undergone surgeries to change their appearance.
❖ Editing photographs by denoising images, enhancing the existing image data.
❖ In the drug discovery process.
❖ Tumor detection in human bodies, and applying filters on Instagram, Faceapp, etc.
Generative Models
Generative adversarial networks (GANs)
GANs achieve this level of realism by pairing a generator, which learns to produce the target output,
with a discriminator, which learns to distinguish true data from the output of the generator. The
generator tries to fool the discriminator, and the discriminator tries to keep from being fooled.
Source
Drawbacks of GANs
❖ Unstable training and mode collapse,
❖ autoregressive models generally suffer from slow synthesis speed.
Diffusion Models
❖ Diffusion models, originally proposed in 2015, have seen a recent revival in interest due to
their training stability and their promising sample quality results on image and audio
generation.
❖ Diffusion models work by corrupting the training data by progressively adding Gaussian noise,
slowly wiping out details in the data until it becomes pure noise, and then training a neural
network to reverse this corruption process.
❖ Running this reversed corruption process synthesizes data from pure noise by gradually
The debate: which is better?
❖ Being likelihood-based models, heavily using parameter sharing, they can model highly
complex distributions of natural images and overcome the drawbacks of AR models and GANs.
❖ Still Evaluating and optimizing these models in pixel space, however, has the downside of low
inference speed and very high training costs
❖ We address both drawbacks with our proposed LDMs, which work on a compressed latent
space of lower dimensionality.
Latent Diffusion Models
Just like any likelihood-based model, learning can be divided into two stages:
1. Perceptual Image Compression
2. Generative Modeling of Latent Representations
Advantages:
❖ By leaving the high-dimensional image space, we obtain DMs which are computationally much
more efficient because sampling is performed on a low-dimensional space.
❖ We exploit the inductive bias of DMs inherited from their UNet architecture which makes them
particularly effective for data with spatial structure.
❖ Finally, we obtain general-purpose compression models whose latent space can be used to train
multiple generative models and which can also be utilized for other downstream applications
such as single-image CLIP-guided synthesis
Experiments and results:
❖ After getting trained unconditional models of images on CelebA-HQ, FFHQ , LSUN-Churches,
and -Bedrooms [102], the sample quality and their coverage of the data manifold were
evaluated using ii) FID and ii) Precision-and-Recall.
❖ We can see On CelebA-HQ, reports a new state-of-the-art FID of 5.11, outperforming previous
likelihood-based models and GANs.
Conclusion
As proposed by the Paper, latent diffusion models are a simple and efficient way that improve both
the training and sampling efficiency of denoising diffusion models while retaining their quality.
References:
https://paperswithcode.com/paper/high-resolution-image-synthesis-with-latent
https://arxiv.org/pdf/2112.10752v2.pdf
https://www.analyticsinsight.net/understanding-importance-generative-adversarial-networks-gans/
https://analyticsindiamag.com/diffusion-models-vs-gans-which-one-to-choose-for-image-synthesis/

Mais conteúdo relacionado

Mais procurados

Mobilenetv1 v2 slide
Mobilenetv1 v2 slideMobilenetv1 v2 slide
Mobilenetv1 v2 slide威智 黃
 
Tutorial on Deep Generative Models
 Tutorial on Deep Generative Models Tutorial on Deep Generative Models
Tutorial on Deep Generative ModelsMLReview
 
PR-409: Denoising Diffusion Probabilistic Models
PR-409: Denoising Diffusion Probabilistic ModelsPR-409: Denoising Diffusion Probabilistic Models
PR-409: Denoising Diffusion Probabilistic ModelsHyeongmin Lee
 
Unified Approach to Interpret Machine Learning Model: SHAP + LIME
Unified Approach to Interpret Machine Learning Model: SHAP + LIMEUnified Approach to Interpret Machine Learning Model: SHAP + LIME
Unified Approach to Interpret Machine Learning Model: SHAP + LIMEDatabricks
 
PR-231: A Simple Framework for Contrastive Learning of Visual Representations
PR-231: A Simple Framework for Contrastive Learning of Visual RepresentationsPR-231: A Simple Framework for Contrastive Learning of Visual Representations
PR-231: A Simple Framework for Contrastive Learning of Visual RepresentationsJinwon Lee
 
Yurii Pashchenko: Zero-shot learning capabilities of CLIP model from OpenAI
Yurii Pashchenko: Zero-shot learning capabilities of CLIP model from OpenAIYurii Pashchenko: Zero-shot learning capabilities of CLIP model from OpenAI
Yurii Pashchenko: Zero-shot learning capabilities of CLIP model from OpenAILviv Startup Club
 
Generative adversarial networks
Generative adversarial networksGenerative adversarial networks
Generative adversarial networksYunjey Choi
 
ViT (Vision Transformer) Review [CDM]
ViT (Vision Transformer) Review [CDM]ViT (Vision Transformer) Review [CDM]
ViT (Vision Transformer) Review [CDM]Dongmin Choi
 
Generative Models for General Audiences
Generative Models for General AudiencesGenerative Models for General Audiences
Generative Models for General AudiencesSangwoo Mo
 
Generative Adversarial Networks
Generative Adversarial NetworksGenerative Adversarial Networks
Generative Adversarial NetworksMark Chang
 
A Style-Based Generator Architecture for Generative Adversarial Networks
A Style-Based Generator Architecture for Generative Adversarial NetworksA Style-Based Generator Architecture for Generative Adversarial Networks
A Style-Based Generator Architecture for Generative Adversarial Networksivaderivader
 
Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)Appsilon Data Science
 
PR-302: NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
PR-302: NeRF: Representing Scenes as Neural Radiance Fields for View SynthesisPR-302: NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
PR-302: NeRF: Representing Scenes as Neural Radiance Fields for View SynthesisHyeongmin Lee
 
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...Simplilearn
 
GANs Deep Learning Summer School
GANs Deep Learning Summer SchoolGANs Deep Learning Summer School
GANs Deep Learning Summer SchoolRubens Zimbres, PhD
 
Generative adversarial networks
Generative adversarial networksGenerative adversarial networks
Generative adversarial networks남주 김
 
GAN - Theory and Applications
GAN - Theory and ApplicationsGAN - Theory and Applications
GAN - Theory and ApplicationsEmanuele Ghelfi
 
Generative Adversarial Networks (GAN)
Generative Adversarial Networks (GAN)Generative Adversarial Networks (GAN)
Generative Adversarial Networks (GAN)Manohar Mukku
 

Mais procurados (20)

Mobilenetv1 v2 slide
Mobilenetv1 v2 slideMobilenetv1 v2 slide
Mobilenetv1 v2 slide
 
Tutorial on Deep Generative Models
 Tutorial on Deep Generative Models Tutorial on Deep Generative Models
Tutorial on Deep Generative Models
 
PR-409: Denoising Diffusion Probabilistic Models
PR-409: Denoising Diffusion Probabilistic ModelsPR-409: Denoising Diffusion Probabilistic Models
PR-409: Denoising Diffusion Probabilistic Models
 
Unified Approach to Interpret Machine Learning Model: SHAP + LIME
Unified Approach to Interpret Machine Learning Model: SHAP + LIMEUnified Approach to Interpret Machine Learning Model: SHAP + LIME
Unified Approach to Interpret Machine Learning Model: SHAP + LIME
 
PR-231: A Simple Framework for Contrastive Learning of Visual Representations
PR-231: A Simple Framework for Contrastive Learning of Visual RepresentationsPR-231: A Simple Framework for Contrastive Learning of Visual Representations
PR-231: A Simple Framework for Contrastive Learning of Visual Representations
 
Yurii Pashchenko: Zero-shot learning capabilities of CLIP model from OpenAI
Yurii Pashchenko: Zero-shot learning capabilities of CLIP model from OpenAIYurii Pashchenko: Zero-shot learning capabilities of CLIP model from OpenAI
Yurii Pashchenko: Zero-shot learning capabilities of CLIP model from OpenAI
 
Swin transformer
Swin transformerSwin transformer
Swin transformer
 
Generative adversarial networks
Generative adversarial networksGenerative adversarial networks
Generative adversarial networks
 
Generative models
Generative modelsGenerative models
Generative models
 
ViT (Vision Transformer) Review [CDM]
ViT (Vision Transformer) Review [CDM]ViT (Vision Transformer) Review [CDM]
ViT (Vision Transformer) Review [CDM]
 
Generative Models for General Audiences
Generative Models for General AudiencesGenerative Models for General Audiences
Generative Models for General Audiences
 
Generative Adversarial Networks
Generative Adversarial NetworksGenerative Adversarial Networks
Generative Adversarial Networks
 
A Style-Based Generator Architecture for Generative Adversarial Networks
A Style-Based Generator Architecture for Generative Adversarial NetworksA Style-Based Generator Architecture for Generative Adversarial Networks
A Style-Based Generator Architecture for Generative Adversarial Networks
 
Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)
 
PR-302: NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
PR-302: NeRF: Representing Scenes as Neural Radiance Fields for View SynthesisPR-302: NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
PR-302: NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
 
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
 
GANs Deep Learning Summer School
GANs Deep Learning Summer SchoolGANs Deep Learning Summer School
GANs Deep Learning Summer School
 
Generative adversarial networks
Generative adversarial networksGenerative adversarial networks
Generative adversarial networks
 
GAN - Theory and Applications
GAN - Theory and ApplicationsGAN - Theory and Applications
GAN - Theory and Applications
 
Generative Adversarial Networks (GAN)
Generative Adversarial Networks (GAN)Generative Adversarial Networks (GAN)
Generative Adversarial Networks (GAN)
 

Semelhante a LDM_ImageSythesis.pptx

Image Masking.pdf
Image Masking.pdfImage Masking.pdf
Image Masking.pdffarin11
 
Model Based Emotion Detection using Point Clouds
Model Based Emotion Detection using Point CloudsModel Based Emotion Detection using Point Clouds
Model Based Emotion Detection using Point CloudsLakshmi Sarvani Videla
 
10.1.1.2.8373
10.1.1.2.837310.1.1.2.8373
10.1.1.2.8373snona
 
Learning from Simulated and Unsupervised Images through Adversarial Training....
Learning from Simulated and Unsupervised Images through Adversarial Training....Learning from Simulated and Unsupervised Images through Adversarial Training....
Learning from Simulated and Unsupervised Images through Adversarial Training....eraser Juan José Calderón
 
GANs Presentation.pptx
GANs Presentation.pptxGANs Presentation.pptx
GANs Presentation.pptxMAHMOUD729246
 
Face-GAN project report.pptx
Face-GAN project report.pptxFace-GAN project report.pptx
Face-GAN project report.pptxAndleebFatima16
 
DendroMap Visual Exploration of Large-Scale Image Datasets for Machine Learni...
DendroMap Visual Exploration of Large-Scale Image Datasets for Machine Learni...DendroMap Visual Exploration of Large-Scale Image Datasets for Machine Learni...
DendroMap Visual Exploration of Large-Scale Image Datasets for Machine Learni...OKOKPROJECTS
 
Report of Previous Project by Yifan Guo
Report of Previous Project by Yifan GuoReport of Previous Project by Yifan Guo
Report of Previous Project by Yifan GuoYifan Guo
 
Face recognition system
Face recognition systemFace recognition system
Face recognition systemYogesh Lamture
 
Face recognition using laplacianfaces
Face recognition using laplacianfaces Face recognition using laplacianfaces
Face recognition using laplacianfaces StudsPlanet.com
 
Password Authentication Framework Based on Encrypted Negative Password
Password Authentication Framework Based on Encrypted Negative PasswordPassword Authentication Framework Based on Encrypted Negative Password
Password Authentication Framework Based on Encrypted Negative PasswordIJSRED
 
[Paper Review] MisGAN: Learning from Incomplete Data with Generative Adversar...
[Paper Review] MisGAN: Learning from Incomplete Data with Generative Adversar...[Paper Review] MisGAN: Learning from Incomplete Data with Generative Adversar...
[Paper Review] MisGAN: Learning from Incomplete Data with Generative Adversar...Jihoo Kim
 
DESIGN AND EVALUATION OF IMAGE DENOISING USING GENERATIVE ADVERSARIAL NETWORK...
DESIGN AND EVALUATION OF IMAGE DENOISING USING GENERATIVE ADVERSARIAL NETWORK...DESIGN AND EVALUATION OF IMAGE DENOISING USING GENERATIVE ADVERSARIAL NETWORK...
DESIGN AND EVALUATION OF IMAGE DENOISING USING GENERATIVE ADVERSARIAL NETWORK...JoshuaAlexMbaya
 
IEEE Pattern analysis and machine intelligence 2016 Title and Abstract
IEEE Pattern analysis and machine intelligence 2016 Title and AbstractIEEE Pattern analysis and machine intelligence 2016 Title and Abstract
IEEE Pattern analysis and machine intelligence 2016 Title and Abstracttsysglobalsolutions
 
TEXT GENERATION WITH GAN NETWORKS USING FEEDBACK SCORE
TEXT GENERATION WITH GAN NETWORKS USING FEEDBACK SCORETEXT GENERATION WITH GAN NETWORKS USING FEEDBACK SCORE
TEXT GENERATION WITH GAN NETWORKS USING FEEDBACK SCOREIJCI JOURNAL
 
An Extensive Review on Generative Adversarial Networks GAN’s
An Extensive Review on Generative Adversarial Networks GAN’sAn Extensive Review on Generative Adversarial Networks GAN’s
An Extensive Review on Generative Adversarial Networks GAN’sijtsrd
 
IRJET - Deep Learning Approach to Inpainting and Outpainting System
IRJET -  	  Deep Learning Approach to Inpainting and Outpainting SystemIRJET -  	  Deep Learning Approach to Inpainting and Outpainting System
IRJET - Deep Learning Approach to Inpainting and Outpainting SystemIRJET Journal
 
Vision based non-invasive tool for facial swelling assessment
Vision based non-invasive tool for facial swelling assessment Vision based non-invasive tool for facial swelling assessment
Vision based non-invasive tool for facial swelling assessment University of Moratuwa
 

Semelhante a LDM_ImageSythesis.pptx (20)

Image Masking.pdf
Image Masking.pdfImage Masking.pdf
Image Masking.pdf
 
Model Based Emotion Detection using Point Clouds
Model Based Emotion Detection using Point CloudsModel Based Emotion Detection using Point Clouds
Model Based Emotion Detection using Point Clouds
 
10.1.1.2.8373
10.1.1.2.837310.1.1.2.8373
10.1.1.2.8373
 
Learning from Simulated and Unsupervised Images through Adversarial Training....
Learning from Simulated and Unsupervised Images through Adversarial Training....Learning from Simulated and Unsupervised Images through Adversarial Training....
Learning from Simulated and Unsupervised Images through Adversarial Training....
 
GANs Presentation.pptx
GANs Presentation.pptxGANs Presentation.pptx
GANs Presentation.pptx
 
Face-GAN project report.pptx
Face-GAN project report.pptxFace-GAN project report.pptx
Face-GAN project report.pptx
 
Face-GAN project report
Face-GAN project reportFace-GAN project report
Face-GAN project report
 
DendroMap Visual Exploration of Large-Scale Image Datasets for Machine Learni...
DendroMap Visual Exploration of Large-Scale Image Datasets for Machine Learni...DendroMap Visual Exploration of Large-Scale Image Datasets for Machine Learni...
DendroMap Visual Exploration of Large-Scale Image Datasets for Machine Learni...
 
Report of Previous Project by Yifan Guo
Report of Previous Project by Yifan GuoReport of Previous Project by Yifan Guo
Report of Previous Project by Yifan Guo
 
Face recognition system
Face recognition systemFace recognition system
Face recognition system
 
Face recognition using laplacianfaces
Face recognition using laplacianfaces Face recognition using laplacianfaces
Face recognition using laplacianfaces
 
Password Authentication Framework Based on Encrypted Negative Password
Password Authentication Framework Based on Encrypted Negative PasswordPassword Authentication Framework Based on Encrypted Negative Password
Password Authentication Framework Based on Encrypted Negative Password
 
[Paper Review] MisGAN: Learning from Incomplete Data with Generative Adversar...
[Paper Review] MisGAN: Learning from Incomplete Data with Generative Adversar...[Paper Review] MisGAN: Learning from Incomplete Data with Generative Adversar...
[Paper Review] MisGAN: Learning from Incomplete Data with Generative Adversar...
 
DESIGN AND EVALUATION OF IMAGE DENOISING USING GENERATIVE ADVERSARIAL NETWORK...
DESIGN AND EVALUATION OF IMAGE DENOISING USING GENERATIVE ADVERSARIAL NETWORK...DESIGN AND EVALUATION OF IMAGE DENOISING USING GENERATIVE ADVERSARIAL NETWORK...
DESIGN AND EVALUATION OF IMAGE DENOISING USING GENERATIVE ADVERSARIAL NETWORK...
 
IEEE Pattern analysis and machine intelligence 2016 Title and Abstract
IEEE Pattern analysis and machine intelligence 2016 Title and AbstractIEEE Pattern analysis and machine intelligence 2016 Title and Abstract
IEEE Pattern analysis and machine intelligence 2016 Title and Abstract
 
TEXT GENERATION WITH GAN NETWORKS USING FEEDBACK SCORE
TEXT GENERATION WITH GAN NETWORKS USING FEEDBACK SCORETEXT GENERATION WITH GAN NETWORKS USING FEEDBACK SCORE
TEXT GENERATION WITH GAN NETWORKS USING FEEDBACK SCORE
 
An Extensive Review on Generative Adversarial Networks GAN’s
An Extensive Review on Generative Adversarial Networks GAN’sAn Extensive Review on Generative Adversarial Networks GAN’s
An Extensive Review on Generative Adversarial Networks GAN’s
 
IRJET - Deep Learning Approach to Inpainting and Outpainting System
IRJET -  	  Deep Learning Approach to Inpainting and Outpainting SystemIRJET -  	  Deep Learning Approach to Inpainting and Outpainting System
IRJET - Deep Learning Approach to Inpainting and Outpainting System
 
Vision based non-invasive tool for facial swelling assessment
Vision based non-invasive tool for facial swelling assessment Vision based non-invasive tool for facial swelling assessment
Vision based non-invasive tool for facial swelling assessment
 
Deep Generative Models - Kevin McGuinness - UPC Barcelona 2018
Deep Generative Models - Kevin McGuinness - UPC Barcelona 2018Deep Generative Models - Kevin McGuinness - UPC Barcelona 2018
Deep Generative Models - Kevin McGuinness - UPC Barcelona 2018
 

Último

FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfMarinCaroMartnezBerg
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Callshivangimorya083
 
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...Suhani Kapoor
 
B2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxB2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxStephen266013
 
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al BarshaAl Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al BarshaAroojKhan71
 
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...Suhani Kapoor
 
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service AmravatiVIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service AmravatiSuhani Kapoor
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationshipsccctableauusergroup
 
VidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptxVidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptxolyaivanovalion
 
Smarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxSmarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxolyaivanovalion
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Callshivangimorya083
 
RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998YohFuh
 
定制英国白金汉大学毕业证(UCB毕业证书) 成绩单原版一比一
定制英国白金汉大学毕业证(UCB毕业证书)																			成绩单原版一比一定制英国白金汉大学毕业证(UCB毕业证书)																			成绩单原版一比一
定制英国白金汉大学毕业证(UCB毕业证书) 成绩单原版一比一ffjhghh
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptxAnupama Kate
 
Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxJohnnyPlasten
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxBPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxMohammedJunaid861692
 
Mature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxMature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxolyaivanovalion
 
BabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxBabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxolyaivanovalion
 
Unveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data AnalystUnveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data AnalystSamantha Rae Coolbeth
 

Último (20)

FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdf
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
 
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
 
B2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxB2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docx
 
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al BarshaAl Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
 
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
 
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service AmravatiVIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships
 
VidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptxVidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptx
 
Smarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxSmarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptx
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
 
RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998
 
定制英国白金汉大学毕业证(UCB毕业证书) 成绩单原版一比一
定制英国白金汉大学毕业证(UCB毕业证书)																			成绩单原版一比一定制英国白金汉大学毕业证(UCB毕业证书)																			成绩单原版一比一
定制英国白金汉大学毕业证(UCB毕业证书) 成绩单原版一比一
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx
 
Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptx
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxBPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
 
Mature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxMature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptx
 
BabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxBabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptx
 
Unveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data AnalystUnveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data Analyst
 

LDM_ImageSythesis.pptx

  • 1. Latent Diffusion Models for High Resolution Image Synthesis -Akanksha Rawat SJSU Master’s Student
  • 2. Image Generation/Synthesis Generates new images from an existing dataset. For example, GANs can create images that look like photographs of human faces, even though the faces don't belong to any real person. source:
  • 3. Why it is important: Application areas ❖ Generating synthetic training data if training data is insufficient or collecting it is too costly, generating human faces and objects in 2D and 3D. ❖ Now with AI being universal, the application extends to using image reconstruction to identify if someone have undergone surgeries to change their appearance. ❖ Editing photographs by denoising images, enhancing the existing image data. ❖ In the drug discovery process. ❖ Tumor detection in human bodies, and applying filters on Instagram, Faceapp, etc.
  • 5. Generative adversarial networks (GANs) GANs achieve this level of realism by pairing a generator, which learns to produce the target output, with a discriminator, which learns to distinguish true data from the output of the generator. The generator tries to fool the discriminator, and the discriminator tries to keep from being fooled. Source
  • 6. Drawbacks of GANs ❖ Unstable training and mode collapse, ❖ autoregressive models generally suffer from slow synthesis speed.
  • 7. Diffusion Models ❖ Diffusion models, originally proposed in 2015, have seen a recent revival in interest due to their training stability and their promising sample quality results on image and audio generation. ❖ Diffusion models work by corrupting the training data by progressively adding Gaussian noise, slowly wiping out details in the data until it becomes pure noise, and then training a neural network to reverse this corruption process. ❖ Running this reversed corruption process synthesizes data from pure noise by gradually
  • 8. The debate: which is better? ❖ Being likelihood-based models, heavily using parameter sharing, they can model highly complex distributions of natural images and overcome the drawbacks of AR models and GANs. ❖ Still Evaluating and optimizing these models in pixel space, however, has the downside of low inference speed and very high training costs ❖ We address both drawbacks with our proposed LDMs, which work on a compressed latent space of lower dimensionality.
  • 9. Latent Diffusion Models Just like any likelihood-based model, learning can be divided into two stages: 1. Perceptual Image Compression 2. Generative Modeling of Latent Representations
  • 10.
  • 11. Advantages: ❖ By leaving the high-dimensional image space, we obtain DMs which are computationally much more efficient because sampling is performed on a low-dimensional space. ❖ We exploit the inductive bias of DMs inherited from their UNet architecture which makes them particularly effective for data with spatial structure. ❖ Finally, we obtain general-purpose compression models whose latent space can be used to train multiple generative models and which can also be utilized for other downstream applications such as single-image CLIP-guided synthesis
  • 12. Experiments and results: ❖ After getting trained unconditional models of images on CelebA-HQ, FFHQ , LSUN-Churches, and -Bedrooms [102], the sample quality and their coverage of the data manifold were evaluated using ii) FID and ii) Precision-and-Recall. ❖ We can see On CelebA-HQ, reports a new state-of-the-art FID of 5.11, outperforming previous likelihood-based models and GANs.
  • 13.
  • 14.
  • 15.
  • 16. Conclusion As proposed by the Paper, latent diffusion models are a simple and efficient way that improve both the training and sampling efficiency of denoising diffusion models while retaining their quality.